问题是如何将wstring转换为字符串?

我还有一个例子:

#include <string>
#include <iostream>

int main()
{
    std::wstring ws = L"Hello";
    std::string s( ws.begin(), ws.end() );

  //std::cout <<"std::string =     "<<s<<std::endl;
    std::wcout<<"std::wstring =    "<<ws<<std::endl;
    std::cout <<"std::string =     "<<s<<std::endl;
}

带注释的输出为:

std::string =     Hello
std::wstring =    Hello
std::string =     Hello

但是without只是:

std::wstring =    Hello

这个例子中有什么问题吗?我可以像上面那样进行转换吗?

EDIT

新例子(考虑到一些答案)是

#include <string>
#include <iostream>
#include <sstream>
#include <locale>

int main()
{
    setlocale(LC_CTYPE, "");

    const std::wstring ws = L"Hello";
    const std::string s( ws.begin(), ws.end() );

    std::cout<<"std::string =     "<<s<<std::endl;
    std::wcout<<"std::wstring =    "<<ws<<std::endl;

    std::stringstream ss;
    ss << ws.c_str();
    std::cout<<"std::stringstream =     "<<ss.str()<<std::endl;
}

输出结果为:

std::string =     Hello
std::wstring =    Hello
std::stringstream =     0x860283c

因此,不能使用stringstream将wstring转换为string。


当前回答

下面是一个基于其他建议的解决方案:

#include <string>
#include <iostream>
#include <clocale>
#include <locale>
#include <vector>

int main() {
  std::setlocale(LC_ALL, "");
  const std::wstring ws = L"ħëłlö";
  const std::locale locale("");
  typedef std::codecvt<wchar_t, char, std::mbstate_t> converter_type;
  const converter_type& converter = std::use_facet<converter_type>(locale);
  std::vector<char> to(ws.length() * converter.max_length());
  std::mbstate_t state;
  const wchar_t* from_next;
  char* to_next;
  const converter_type::result result = converter.out(state, ws.data(), ws.data() + ws.length(), from_next, &to[0], &to[0] + to.size(), to_next);
  if (result == converter_type::ok or result == converter_type::noconv) {
    const std::string s(&to[0], to_next);
    std::cout <<"std::string =     "<<s<<std::endl;
  }
}

这通常适用于Linux,但会在Windows上产生问题。

其他回答

而不是包括locale和所有那些花哨的东西,如果你知道为FACT你的字符串是可转换的,只需这样做:

#include <iostream>
#include <string>

using namespace std;

int main()
{
  wstring w(L"bla");
  string result;
  for(char x : w)
    result += x;

  cout << result << '\n';
}

这里有一个活生生的例子

除了转换类型之外,还应该注意字符串的实际格式。

当编译多字节字符集Visual Studio和Win API时,假设UTF8(实际上是windows编码,即windows -28591)。 当为Unicode字符集Visual studio和Win API编译时,假设UTF16。

因此,您必须将字符串从UTF16转换为UTF8格式,而不仅仅是转换为std::string。 当使用多字符格式(如一些非拉丁语言)时,这将是必要的。

其思想是确定std::wstring总是表示UTF16。 std::string总是表示UTF8。

这不是由编译器强制执行的,这是一个更好的策略。 注意我用来定义UTF16 (L)和UTF8 (u8)的字符串前缀。

要在两种类型之间进行转换,您应该使用:std::codecvt_utf8_utf16< wchar_t>

#include <string>

#include <codecvt>

int main()
{

    std::string original8 = u8"הלו";

    std::wstring original16 = L"הלו";

    //C++11 format converter
    std::wstring_convert<std::codecvt_utf8_utf16<wchar_t>> convert;

    //convert to UTF8 and std::string
    std::string utf8NativeString = convert.to_bytes(original16);

    std::wstring utf16NativeString = convert.from_bytes(original8);

    assert(utf8NativeString == original8);
    assert(utf16NativeString == original16);

    return 0;
}

我相信官方的方法仍然是使用codecvt facet(您需要某种语言环境感知的转换),例如

resultCode = use_facet<codecvt<char, wchar_t, ConversionState> >(locale).
  in(stateVar, scratchbuffer, scratchbufferEnd, from, to, toLimit, curPtr);

或者类似的东西,我没有工作代码。但我不确定现在有多少人使用这种机器,有多少人只是要求内存指针,让ICU或其他库处理血腥的细节。

代码有两个问题:

The conversion in const std::string s( ws.begin(), ws.end() ); is not required to correctly map the wide characters to their narrow counterpart. Most likely, each wide character will just be typecast to char. The resolution to this problem is already given in the answer by kem and involves the narrow function of the locale's ctype facet. You are writing output to both std::cout and std::wcout in the same program. Both cout and wcout are associated with the same stream (stdout) and the results of using the same stream both as a byte-oriented stream (as cout does) and a wide-oriented stream (as wcout does) are not defined. The best option is to avoid mixing narrow and wide output to the same (underlying) stream. For stdout/cout/wcout, you can try switching the orientation of stdout when switching between wide and narrow output (or vice versa): #include <iostream> #include <stdio.h> #include <wchar.h> int main() { std::cout << "narrow" << std::endl; fwide(stdout, 1); // switch to wide std::wcout << L"wide" << std::endl; fwide(stdout, -1); // switch to narrow std::cout << "narrow" << std::endl; fwide(stdout, 1); // switch to wide std::wcout << L"wide" << std::endl; }

在我的情况下,我必须使用多字节字符(MBCS),我想使用std::string和std::wstring。不能使用c++11。所以我使用mbstowcs和wcstombs。

我与使用new, delete[]做相同的函数,但它比这更慢。

这可以帮助如何:在各种字符串类型之间转换

EDIT

然而,在转换为wstring和源字符串是没有字母和多字节字符串的情况下,它是不工作的。 所以我把wcstombs改成WideCharToMultiByte。

#include <string>

std::wstring get_wstr_from_sz(const char* psz)
{
    //I think it's enough to my case
    wchar_t buf[0x400];
    wchar_t *pbuf = buf;
    size_t len = strlen(psz) + 1;

    if (len >= sizeof(buf) / sizeof(wchar_t))
    {
        pbuf = L"error";
    }
    else
    {
        size_t converted;
        mbstowcs_s(&converted, buf, psz, _TRUNCATE);
    }

    return std::wstring(pbuf);
}

std::string get_string_from_wsz(const wchar_t* pwsz)
{
    char buf[0x400];
    char *pbuf = buf;
    size_t len = wcslen(pwsz)*2 + 1;

    if (len >= sizeof(buf))
    {
        pbuf = "error";
    }
    else
    {
        size_t converted;
        wcstombs_s(&converted, buf, pwsz, _TRUNCATE);
    }

    return std::string(pbuf);
}

编辑使用“MultiByteToWideChar”而不是“wcstombs”

#include <Windows.h>
#include <boost/shared_ptr.hpp>
#include "string_util.h"

std::wstring get_wstring_from_sz(const char* psz)
{
    int res;
    wchar_t buf[0x400];
    wchar_t *pbuf = buf;
    boost::shared_ptr<wchar_t[]> shared_pbuf;

    res = MultiByteToWideChar(CP_ACP, 0, psz, -1, buf, sizeof(buf)/sizeof(wchar_t));

    if (0 == res && GetLastError() == ERROR_INSUFFICIENT_BUFFER)
    {
        res = MultiByteToWideChar(CP_ACP, 0, psz, -1, NULL, 0);

        shared_pbuf = boost::shared_ptr<wchar_t[]>(new wchar_t[res]);

        pbuf = shared_pbuf.get();

        res = MultiByteToWideChar(CP_ACP, 0, psz, -1, pbuf, res);
    }
    else if (0 == res)
    {
        pbuf = L"error";
    }

    return std::wstring(pbuf);
}

std::string get_string_from_wcs(const wchar_t* pcs)
{
    int res;
    char buf[0x400];
    char* pbuf = buf;
    boost::shared_ptr<char[]> shared_pbuf;

    res = WideCharToMultiByte(CP_ACP, 0, pcs, -1, buf, sizeof(buf), NULL, NULL);

    if (0 == res && GetLastError() == ERROR_INSUFFICIENT_BUFFER)
    {
        res = WideCharToMultiByte(CP_ACP, 0, pcs, -1, NULL, 0, NULL, NULL);

        shared_pbuf = boost::shared_ptr<char[]>(new char[res]);

        pbuf = shared_pbuf.get();

        res = WideCharToMultiByte(CP_ACP, 0, pcs, -1, pbuf, res, NULL, NULL);
    }
    else if (0 == res)
    {
        pbuf = "error";
    }

    return std::string(pbuf);
}